• KEPCO Journal on Electric Power and Energy
• /
• 제7권2호
• /
• pp.323-328
• /
• 2021

Diagnostic models are required. Data augmentation is one of the best ways to improve deep learning performance. Traditional augmentation techniques that modify image brightness or spatial information are difficult to achieve great results. To overcome this, a generative adversarial network (GAN) technology that generates virtual data to increase deep learning performance has emerged. GAN can create realistic-looking fake images by competitive learning two networks, a generator that creates fakes and a discriminator that determines whether images are real or fake made by the generator. GAN is being used in computer vision, IT solutions, and medical imaging fields. It is essential to secure additional learning data to advance deep learning-based fault diagnosis solutions in the power industry where facilities are strictly maintained more than other industries. In this paper, we propose a method for generating power facility images using GAN and a strategy for improving performance when only used a small amount of data. Finally, we analyze the performance of the augmented image to see if it could be utilized for the deep learning-based diagnosis system or not.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.150-153
• /
• 2003

As the web is vast and disorderly, it is difficult to find desired information on the web. In particular, finding image resources (knowing where and what kind of images can be found on the web) is very difficult but challenging. As the first step towards the web resource mining, this paper reports the preliminary results of collecting a number of images by a web robot as well as presenting those meta information.

• Journal of Information Processing Systems
• /
• 제13권2호
• /
• pp.204-214
• /
• 2017

Artificial intelligence, especially deep learning technology, is penetrating the majority of research areas, including the field of bioinformatics. However, deep learning has some limitations, such as the complexity of parameter tuning, architecture design, and so forth. In this study, we analyze these issues and challenges in regards to its applications in bioinformatics, particularly genomic analysis and medical image analytics, and give the corresponding approaches and solutions. Although these solutions are mostly rule of thumb, they can effectively handle the issues connected to training learning machines. As such, we explore the tendency of deep learning technology by examining several directions, such as automation, scalability, individuality, mobility, integration, and intelligence warehousing.

• 대한안전경영과학회지
• /
• 제13권3호
• /
• pp.169-174
• /
• 2011

The purpose of this study was to clarify the impact of national and corporate brand image of Korea on chinese consumers' purchasing Intention, also the impact of China on korean consumers' purchasing Intention. And the second aim of the research is to provide Korean businessmen who are interested in chinese market with information about chinese consumers' purchasing behaviour. Data from 205 chinese and korean consumers were analysed. As the result of analyses, it was found that Korean country image positive affects corporate brand image(samsung) and Chinese country image negative affects corporate brand image(haier) and product image. Korean corporate brand image only affects product image on chinese consumers. The product image affects Korean and Chinese consumer's purchasing intention.

• 전기학회논문지
• /
• 제62권2호
• /
• pp.257-263
• /
• 2013

In case of image observation equipments, CCTV for short distance visual field is usually installed and operated mostly as the means of crime-prevention. However, the extensive demand for monitoring problems in case of the increase in intelligent crimes and disasters has led to the necessity of the development of long-distance observation equipments embedded with Night View functions. In case of the Night View equipments, the relevant market is set up to be focused mostly on Thermal Observation Device(hereinafter, TOD), but some shortcomings such as the limitation of image visibility and excessive maintenance cost, etc. have actually caused the necessity of new long distance Night View equipment. Moreover there might follow lots of difficulties in long-distance visualization in the event that irregular reflection is generated by minute particles in the atmosphere such as fog, smog, and dust, etc. These factors are motivate the work presented in this study. Our study is aimed at the realization of Pulsed Laser Illuminator and newly proposed Range-Gated image acquisition technology. And also the implementation of Tracker for continuous trace of the objects of interest from the obtained sequence images.

• 디지털산업정보학회논문지
• /
• 제10권2호
• /
• pp.143-156
• /
• 2014

Comprehensive programming channels are based on recognition of the parent company, their parent newspaper has increased brand awareness. In this paper, the comprehensive channels to look at the structure of the channel brand architecture, a certain brand of newspapers and comprehensive channels have a effect on the formation of the image of the channel according to the future of the brand extension strategy for MPP. Referring to the brand architecture, which reveals the structural system of the brand, it is argued that TV Chosun and MBN take the integrated corporate brand strategy, while JTBC tries to mix and balance the brands of the parent corporation and its own independent one. Exceptionally, Channel A doesn't take a name of its parent corporation 'Dong-A'. It is argued that the comprehensive programming channels utilize and take the parent corporate brand, mixed brand, and independent brand in accordance with circumstances of their own parent corporates. Their parent brand of comprehensive channels give viewers a positive image and awareness of comprehensive channel brand. while building its own channel images, TV Chosun and Channel A Conservative extension of a certain brand marketers to be bound by the channel's image. Brand extension of comprehensive channels is to have the strength of their entry into the genre that is most likely higher.

• 한국가시화정보학회지
• /
• 제19권1호
• /
• pp.28-35
• /
• 2021

In this study, an image processing method for the measurement of two-phase bubbly flow is developed. Shadowgraphy images obtained by high-speed camera are used for analysis. Some bubbles are generated as single unit and others are overlapped or clustered. Single bubbles can be easily analyzed using parameters such as bubble shape, centroid, and area. But overlapped bubbles are difficult to transform clustered bubbles into segmented bubbles. Several approaches were proposed for the bubble segmentation such as Hough transform, connection point method and watershed. These methods are not enough for bubble segmentation. In order to obtain the size distribution of bubbles, we present a method of splitting overlapping bubbles using watershed and approximating them to ellipse. There is only 5% error difference between manual and automatic analysis. Furthermore, the error can be reduced down to 1.2% when a correction factor is used. The ellipse fitting algorithm developed in this study can be used to measure bubble parameters accurately by reflecting the shape of the bubbles.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2004년도 Asia Display / IMID 04
• /
• pp.783-786
• /
• 2004

We have developed a 470 x 235ppi poly-Si TFT LCD with a novel pixel arrangement, called HDDP (Horizontally Double-Density Pixels), for high-resolution 2D and 3D autostereoscopic display. 3D image quality is especially high in a lenticular-lens-equipped 3D mode because both horizontal resolution and vertical resolution are high, and because these resolutions are equal. 3D and 2D images can be displayed simultaneously in the same picture. In addition, 3D images can be displayed anywhere and 2D characters can be made to appear at different depths with perfect legibility. No switching of 2D/3D modes is necessary, and the design's thin and uncomplicated structure makes it especially suitable for mobile terminals.

• 지구물리와물리탐사
• /
• 제7권1호
• /
• pp.56-61
• /
• 2004

In order to image the distribution of permeability in granitic rocks, we carried out two-dimensional (2D) resistivity profiling, together with in-situ permeability tests, electrical logging of boreholes, and resistivity measurements of rock core samples in a laboratory. Based on the electrical logging and in-situ permeability data from boreholes, we obtained empirical equations which relate resistivity and permeability of the granitic rocks in the area studied. We then applied the empirical equation to a 2D resistivity section, to produce a 2D permeability section of the granitic rocks. In this paper, we present details of the field data and of the procedure for conversion from the resistivity section to a permeability section. The observed relationship between resistivity and permeability of the rocks is also discussed.

• 한국산업융합학회 논문집
• /
• 제23권2_2호
• /
• pp.209-218
• /
• 2020

Various studies and business investments have been performed on UAV in the field of spatial information industry, and it is judged that this industry has being evolved into an expansion stage as a legalization progresses. In addition, public institutions such as Korea Land and Geospatial Information Corporation, Korea Expressway Corporation, and Korea Land and Housing Corporation which have relatively much utilized spatial information work have entered into the stage of settling with active introduction for reasons of work efficiency and business management. However, surveying drones are still classified as expensive equipment, which is a burden on general business application and technology popularization. Moreover, the stabilization of reliability of various location information acquired from UAV is a part of ongoing research and supplementation. Therefore, in this study, to use image information acquired from low-cost UAV as reliable spatial information data, the flight altitude was changed and compared with the result of double transverse flight with conventional photographing technique. As a result, there was no change in the result value at low altitude, but the result showed more than 30% accuracy and accuracy improvement for the X, Y value at the altitude of 130m or higher than the conventional method.